An Energy-Efficient Convolutional Neural Network Processor Architecture Based on a Systolic Array
Open Access
- 9 December 2022
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 12 (24) , 12633
Abstract
Deep convolutional neural networks (CNNs) have shown strong abilities in the application of artificial intelligence. However, due to their extensive amount of computation, traditional processors have low energy efficiency when executing CNN algorithms, which is unacceptable for portable devices with limited hardware cost and battery capacity, so designing a CNN-specific processor is necessary. In this paper, we propose an energy-efficient CNN processor architecture for lightweight devices with a processing elements (PEs) array consisting of 384 PEs. Using the systolic array-based PE array, it realizes parallel operations between filter rows and between channels of output feature maps, supporting the acceleration of 3D convolution and fully connected computation with various parameters by configuring internal instruction registers. The computing strategy based on the proposed systolic dataflow achieves less hardware overhead compared with other strategies, and the reuse of image values and weight values, which effectively reduce the power of memory access. A memory system with a multi-level storage structure combined with register file (RF) and SRAM is used in the proposed CNN processor, which further reduces the energy overhead of computing. The proposed CNN processor architecture has been verified on a ZC706 FPGA platform using VGG-16 based on the proposed image segmentation method, the evaluation results indicate that the peak throughput achieves 115.2 GOP/s consuming 3.801 W at 150 MHz, energy efficiency and DSP efficiency reaches 30.32 GOP/s/W and 0.26 GOP/s/DSP, respectively.Keywords
Funding Information
- Shenzhen Science & Technology Innovation Commission (JCYJ20200109120404043, 2021KQNCX112)
This publication has 27 references indexed in Scilit:
- Angel-Eye: A Complete Design Flow for Mapping CNN Onto Embedded FPGAIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2018
- A High Energy Efficient Reconfigurable Hybrid Neural Network Processor for Deep Learning ApplicationsIEEE Journal of Solid-State Circuits, 2017
- Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural NetworksIEEE Journal of Solid-State Circuits, 2016
- Origami: A 803-GOp/s/W Convolutional Network AcceleratorIEEE Transactions on Circuits and Systems for Video Technology, 2016
- Deep Residual Learning for Image Recognition2016
- DaDianNao: A Neural Network SupercomputerIEEE Transactions on Computers, 2016
- Going Deeper with Embedded FPGA Platform for Convolutional Neural Network2016
- ShiDianNao2015
- Memory-centric accelerator design for Convolutional Neural Networks2013
- Systolic Arrays for Matrix Transpose and Other ReorderingsIEEE Transactions on Computers, 1987